{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/residual-connection/papers/246","list_of":"/method/residual-connection","method":"Residual Connection","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":246,"pages_in_order":285,"rows_per_page":100,"rows":[24501,24600],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/residual-connection","prev":"/method/residual-connection/papers/245","next":"/method/residual-connection/papers/247","papers":[{"paper":"/paper/conditionally-adaptive-multi-task-learning","slug":"conditionally-adaptive-multi-task-learning","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","date":"2020-09-19","arxiv_id":"2009.09139","n_code_links":1,"syntology":null},{"paper":"/paper/gated-res2net-for-multivariate-time-series","slug":"gated-res2net-for-multivariate-time-series","title":"Gated Res2Net for Multivariate Time Series Analysis","date":"2020-09-19","arxiv_id":"2009.11705","n_code_links":1,"syntology":null},{"paper":null,"slug":"nominal-compound-chain-extraction-a-new-task","title":"Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain","date":"2020-09-19","arxiv_id":"2009.09173","n_code_links":0,"syntology":null},{"paper":null,"slug":"prior-art-search-and-reranking-for-generated","title":"Prior Art Search and Reranking for Generated Patent Text","date":"2020-09-19","arxiv_id":"2009.09132","n_code_links":0,"syntology":null},{"paper":"/paper/towards-computational-linguistics-in","slug":"towards-computational-linguistics-in","title":"Towards Computational Linguistics in Minangkabau Language: Studies on Sentiment Analysis and Machine Translation","date":"2020-09-19","arxiv_id":"2009.09309","n_code_links":1,"syntology":null},{"paper":"/paper/densely-guided-knowledge-distillation-using","slug":"densely-guided-knowledge-distillation-using","title":"Densely Guided Knowledge Distillation using Multiple Teacher Assistants","date":"2020-09-18","arxiv_id":"2009.08825","n_code_links":1,"syntology":null},{"paper":"/paper/fasthan-a-bert-based-joint-many-task-toolkit","slug":"fasthan-a-bert-based-joint-many-task-toolkit","title":"fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP","date":"2020-09-18","arxiv_id":"2009.08633","n_code_links":1,"syntology":null},{"paper":null,"slug":"hardware-accelerator-for-multi-head-attention","title":"Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer","date":"2020-09-18","arxiv_id":"2009.08605","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-gpt-with-congruent-transformers","title":"Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models","date":"2020-09-18","arxiv_id":"2009.08636","n_code_links":0,"syntology":null},{"paper":null,"slug":"neu-at-wnut-2020-task-2-data-augmentation-to","title":"NEU at WNUT-2020 Task 2: Data Augmentation To Tell BERT That Death Is Not Necessarily Informative","date":"2020-09-18","arxiv_id":"2009.08590","n_code_links":0,"syntology":null},{"paper":"/paper/residual-spatial-attention-network-for","slug":"residual-spatial-attention-network-for","title":"Residual Spatial Attention Network for Retinal Vessel Segmentation","date":"2020-09-18","arxiv_id":"2009.08829","n_code_links":1,"syntology":null},{"paper":"/paper/the-birth-of-romanian-bert","slug":"the-birth-of-romanian-bert","title":"The birth of Romanian BERT","date":"2020-09-18","arxiv_id":"2009.08712","n_code_links":1,"syntology":null},{"paper":"/paper/will-it-unblend","slug":"will-it-unblend","title":"Will it Unblend?","date":"2020-09-18","arxiv_id":"2009.09123","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multimodal-memes-classification-a-survey","title":"A Multimodal Memes Classification: A Survey and Open Research Issues","date":"2020-09-17","arxiv_id":"2009.08395","n_code_links":0,"syntology":null},{"paper":"/paper/aag-self-supervised-representation-learning","slug":"aag-self-supervised-representation-learning","title":"AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent Loss","date":"2020-09-17","arxiv_id":"2009.07994","n_code_links":3,"syntology":null},{"paper":null,"slug":"compositional-and-lexical-semantics-in","title":"Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA","date":"2020-09-17","arxiv_id":"2009.08257","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-modal-alignment-with-mixture-experts","title":"Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation","date":"2020-09-17","arxiv_id":"2009.09926","n_code_links":0,"syntology":null},{"paper":"/paper/distilled-one-shot-federated-learning","slug":"distilled-one-shot-federated-learning","title":"Distilled One-Shot Federated Learning","date":"2020-09-17","arxiv_id":"2009.07999","n_code_links":1,"syntology":null},{"paper":"/paper/distributional-generalization-a-new-kind-of","slug":"distributional-generalization-a-new-kind-of","title":"Distributional Generalization: A New Kind of Generalization","date":"2020-09-17","arxiv_id":"2009.08092","n_code_links":1,"syntology":null},{"paper":"/paper/dsc-iit-ism-at-semeval-2020-task-6-boosting","slug":"dsc-iit-ism-at-semeval-2020-task-6-boosting","title":"DSC IIT-ISM at SemEval-2020 Task 6: Boosting BERT with Dependencies for Definition Extraction","date":"2020-09-17","arxiv_id":"2009.08180","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-transformer-based-large-scale","title":"Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning","date":"2020-09-17","arxiv_id":"2009.08065","n_code_links":0,"syntology":null},{"paper":"/paper/graphcodebert-pre-training-code","slug":"graphcodebert-pre-training-code","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","date":"2020-09-17","arxiv_id":"2009.08366","n_code_links":1,"syntology":null},{"paper":null,"slug":"label-smoothing-and-adversarial-robustness","title":"Label Smoothing and Adversarial Robustness","date":"2020-09-17","arxiv_id":"2009.08233","n_code_links":0,"syntology":null},{"paper":"/paper/multi-2oie-multilingual-open-information","slug":"multi-2oie-multilingual-open-information","title":"Multi$^2$OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT","date":"2020-09-17","arxiv_id":"2009.08128","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["youngbin-ro/Multi2OIE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-fully-8-bit-integer-inference-for-the","title":"Towards Fully 8-bit Integer Inference for the Transformer Model","date":"2020-09-17","arxiv_id":"2009.08034","n_code_links":0,"syntology":null},{"paper":"/paper/automated-source-code-generation-and-auto","slug":"automated-source-code-generation-and-auto","title":"Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches","date":"2020-09-16","arxiv_id":"2009.07740","n_code_links":1,"syntology":null},{"paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","slug":"cogtree-cognition-tree-loss-for-unbiased","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","date":"2020-09-16","arxiv_id":"2009.07526","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-approaches-for-extracting","title":"Deep Learning Approaches for Extracting Adverse Events and Indications of Dietary Supplements from Clinical Text","date":"2020-09-16","arxiv_id":"2009.07780","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-level-neural-machine-translation-1","title":"Document-level Neural Machine Translation with Document Embeddings","date":"2020-09-16","arxiv_id":"2009.08775","n_code_links":0,"syntology":null},{"paper":null,"slug":"extremely-low-bit-transformer-quantization","title":"Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation","date":"2020-09-16","arxiv_id":"2009.07453","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-to-sequence-neural-machine-translation","title":"Graph-to-Sequence Neural Machine Translation","date":"2020-09-16","arxiv_id":"2009.07489","n_code_links":0,"syntology":null},{"paper":null,"slug":"nabu-multilingual-graph-based-neural-rdf","title":"NABU $\\mathrm{-}$ Multilingual Graph-based Neural RDF Verbalizer","date":"2020-09-16","arxiv_id":"2009.07728","n_code_links":0,"syntology":null},{"paper":"/paper/rcnn-for-region-of-interest-detection-in","slug":"rcnn-for-region-of-interest-detection-in","title":"RCNN for Region of Interest Detection in Whole Slide Images","date":"2020-09-16","arxiv_id":"2009.07532","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrofitting-structure-aware-transformer","title":"Retrofitting Structure-aware Transformer Language Model for End Tasks","date":"2020-09-16","arxiv_id":"2009.07408","n_code_links":0,"syntology":null},{"paper":"/paper/simplified-tinybert-knowledge-distillation","slug":"simplified-tinybert-knowledge-distillation","title":"Simplified TinyBERT: Knowledge Distillation for Document Retrieval","date":"2020-09-16","arxiv_id":"2009.07531","n_code_links":4,"syntology":null},{"paper":null,"slug":"solomon-at-semeval-2020-task-11-ensemble","title":"Solomon at SemEval-2020 Task 11: Ensemble Architecture for Fine-Tuned Propaganda Detection in News Articles","date":"2020-09-16","arxiv_id":"2009.07473","n_code_links":0,"syntology":null},{"paper":"/paper/union-an-unreferenced-metric-for-evaluating","slug":"union-an-unreferenced-metric-for-evaluating","title":"UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation","date":"2020-09-16","arxiv_id":"2009.07602","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["thu-coai/UNION"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/a-mobile-app-for-wound-localization-using","slug":"a-mobile-app-for-wound-localization-using","title":"A Mobile App for Wound Localization using Deep Learning","date":"2020-09-15","arxiv_id":"2009.07133","n_code_links":1,"syntology":null},{"paper":null,"slug":"achieving-real-time-execution-of-transformer","title":"Real-Time Execution of Large-scale Language Models on Mobile","date":"2020-09-15","arxiv_id":"2009.06823","n_code_links":0,"syntology":null},{"paper":"/paper/attention-aware-inference-for-neural","slug":"attention-aware-inference-for-neural","title":"Global-aware Beam Search for Neural Abstractive Summarization","date":"2020-09-15","arxiv_id":"2009.06891","n_code_links":2,"syntology":null},{"paper":null,"slug":"augmented-natural-language-for-generative","title":"Augmented Natural Language for Generative Sequence Labeling","date":"2020-09-15","arxiv_id":"2009.13272","n_code_links":0,"syntology":null},{"paper":"/paper/bert-qe-contextualized-query-expansion-for","slug":"bert-qe-contextualized-query-expansion-for","title":"BERT-QE: Contextualized Query Expansion for Document Re-ranking","date":"2020-09-15","arxiv_id":"2009.07258","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":0,"n_instrument":2,"unverified":9,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","official":{"repos":["zh-zheng/BERT-QE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/critical-thinking-for-language-models","slug":"critical-thinking-for-language-models","title":"Critical Thinking for Language Models","date":"2020-09-15","arxiv_id":"2009.07185","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["debatelab/aacorpus"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/denert-kg-named-entity-and-relation","slug":"denert-kg-named-entity-and-relation","title":"DeNERT-KG: Named Entity and Relation Extraction Model Using DQN, Knowledge Graph, and BERT","date":"2020-09-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dialogue-response-ranking-training-with-large","slug":"dialogue-response-ranking-training-with-large","title":"Dialogue Response Ranking Training with Large-Scale Human Feedback Data","date":"2020-09-15","arxiv_id":"2009.06978","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"event-presence-prediction-helps-trigger","title":"Event Presence Prediction Helps Trigger Detection Across Languages","date":"2020-09-15","arxiv_id":"2009.07188","n_code_links":0,"syntology":null},{"paper":"/paper/it-s-not-just-size-that-matters-small","slug":"it-s-not-just-size-that-matters-small","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","date":"2020-09-15","arxiv_id":"2009.07118","n_code_links":5,"syntology":null},{"paper":null,"slug":"learning-functors-using-gradient-descent","title":"Learning Functors using Gradient Descent","date":"2020-09-15","arxiv_id":"2009.06837","n_code_links":0,"syntology":null},{"paper":null,"slug":"lessons-learned-from-applying-off-the-shelf","title":"Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet","date":"2020-09-15","arxiv_id":"2009.07238","n_code_links":0,"syntology":null},{"paper":"/paper/mlmlm-link-prediction-with-mean-likelihood","slug":"mlmlm-link-prediction-with-mean-likelihood","title":"MLMLM: Link Prediction with Mean Likelihood Masked Language Model","date":"2020-09-15","arxiv_id":"2009.07058","n_code_links":0,"syntology":null},{"paper":"/paper/resnet-like-architecture-with-low-hardware","slug":"resnet-like-architecture-with-low-hardware","title":"ResNet-like Architecture with Low Hardware Requirements","date":"2020-09-15","arxiv_id":"2009.07190","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-radicalization-risks-of-gpt-3-and","title":"The Radicalization Risks of GPT-3 and Advanced Neural Language Models","date":"2020-09-15","arxiv_id":"2009.06807","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-accuracy-roi-driven-data-analytics-of","title":"Beyond Accuracy: ROI-driven Data Analytics of Empirical Data","date":"2020-09-14","arxiv_id":"2009.06492","n_code_links":0,"syntology":null},{"paper":"/paper/can-fine-tuning-pre-trained-models-lead-to","slug":"can-fine-tuning-pre-trained-models-lead-to","title":"On Robustness and Bias Analysis of BERT-based Relation Extraction","date":"2020-09-14","arxiv_id":"2009.06206","n_code_links":1,"syntology":null},{"paper":null,"slug":"controllable-neural-text-to-speech-synthesis","title":"Controllable neural text-to-speech synthesis using intuitive prosodic features","date":"2020-09-14","arxiv_id":"2009.06775","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-and-clustering-for-vehicle","title":"Data Augmentation and Clustering for Vehicle Make/Model Classification","date":"2020-09-14","arxiv_id":"2009.06679","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-transformers-a-survey","title":"Efficient Transformers: A Survey","date":"2020-09-14","arxiv_id":"2009.06732","n_code_links":0,"syntology":null},{"paper":"/paper/filling-the-gap-of-utterance-aware-and","slug":"filling-the-gap-of-utterance-aware-and","title":"Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue","date":"2020-09-14","arxiv_id":"2009.06504","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/gedi-generative-discriminator-guided-sequence","slug":"gedi-generative-discriminator-guided-sequence","title":"GeDi: Generative Discriminator Guided Sequence Generation","date":"2020-09-14","arxiv_id":"2009.06367","n_code_links":3,"syntology":{"ran":6,"of":11,"n_ran_checked":3,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["salesforce/GeDi"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"boostingbert-integrating-multi-class-boosting","title":"BoostingBERT:Integrating Multi-Class Boosting into BERT for NLP Tasks","date":"2020-09-13","arxiv_id":"2009.05959","n_code_links":0,"syntology":null},{"paper":"/paper/cluster-former-clustering-based-sparse","slug":"cluster-former-clustering-based-sparse","title":"Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding","date":"2020-09-13","arxiv_id":"2009.06097","n_code_links":0,"syntology":null},{"paper":"/paper/pairwise-gan-pose-based-view-synthesis","slug":"pairwise-gan-pose-based-view-synthesis","title":"Pairwise-GAN: Pose-based View Synthesis through Pair-Wise Training","date":"2020-09-13","arxiv_id":"2009.06053","n_code_links":1,"syntology":null},{"paper":null,"slug":"cia-nitt-at-wnut-2020-task-2-classification","title":"CIA_NITT at WNUT-2020 Task 2: Classification of COVID-19 Tweets Using Pre-trained Language Models","date":"2020-09-12","arxiv_id":"2009.05782","n_code_links":0,"syntology":null},{"paper":null,"slug":"corrective-feedback-emphatic-speech-synthesis","title":"Visual-speech Synthesis of Exaggerated Corrective Feedback","date":"2020-09-12","arxiv_id":"2009.05748","n_code_links":0,"syntology":null},{"paper":"/paper/country-image-in-covid-19-pandemic-a-case","slug":"country-image-in-covid-19-pandemic-a-case","title":"Country Image in COVID-19 Pandemic: A Case Study of China","date":"2020-09-12","arxiv_id":"2009.05817","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-pre-trained-contextual-embeddings","title":"Fine-tuning Pre-trained Contextual Embeddings for Citation Content Analysis in Scholarly Publication","date":"2020-09-12","arxiv_id":"2009.05836","n_code_links":0,"syntology":null},{"paper":"/paper/yolobile-real-time-object-detection-on-mobile","slug":"yolobile-real-time-object-detection-on-mobile","title":"YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design","date":"2020-09-12","arxiv_id":"2009.05697","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-comparison-of-lstm-and-bert-for-small","title":"A Comparison of LSTM and BERT for Small Corpus","date":"2020-09-11","arxiv_id":"2009.05451","n_code_links":0,"syntology":null},{"paper":"/paper/compressed-deep-networks-goodbye-svd-hello","slug":"compressed-deep-networks-goodbye-svd-hello","title":"Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation","date":"2020-09-11","arxiv_id":"2009.05647","n_code_links":1,"syntology":null},{"paper":null,"slug":"enabling-image-recognition-on-constrained","title":"Enabling Image Recognition on Constrained Devices Using Neural Network Pruning and a CycleGAN","date":"2020-09-11","arxiv_id":"2009.05300","n_code_links":0,"syntology":null},{"paper":"/paper/gtea-representation-learning-for-temporal","slug":"gtea-representation-learning-for-temporal","title":"GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation","date":"2020-09-11","arxiv_id":"2009.05266","n_code_links":2,"syntology":null},{"paper":"/paper/inverse-mapping-of-face-gans","slug":"inverse-mapping-of-face-gans","title":"Inverse mapping of face GANs","date":"2020-09-11","arxiv_id":"2009.05671","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-convolutional-neural-network","title":"An Efficient Quantitative Approach for Optimizing Convolutional Neural Networks","date":"2020-09-11","arxiv_id":"2009.05236","n_code_links":0,"syntology":null},{"paper":null,"slug":"sofar-shortcut-based-fractal-architectures","title":"SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks","date":"2020-09-11","arxiv_id":"2009.05317","n_code_links":0,"syntology":null},{"paper":"/paper/unit-test-case-generation-with-transformers","slug":"unit-test-case-generation-with-transformers","title":"Unit Test Case Generation with Transformers and Focal Context","date":"2020-09-11","arxiv_id":"2009.05617","n_code_links":1,"syntology":null},{"paper":null,"slug":"upb-at-semeval-2020-task-11-propaganda","title":"UPB at SemEval-2020 Task 11: Propaganda Detection with Domain-Specific Trained BERT","date":"2020-09-11","arxiv_id":"2009.05289","n_code_links":0,"syntology":null},{"paper":"/paper/upb-at-semeval-2020-task-6-pretrained","slug":"upb-at-semeval-2020-task-6-pretrained","title":"UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction","date":"2020-09-11","arxiv_id":"2009.05603","n_code_links":3,"syntology":null},{"paper":"/paper/brain2word-decoding-brain-activity-for","slug":"brain2word-decoding-brain-activity-for","title":"Brain2Word: Decoding Brain Activity for Language Generation","date":"2020-09-10","arxiv_id":"2009.04765","n_code_links":1,"syntology":null},{"paper":"/paper/comprehensive-comparison-of-deep-learning","slug":"comprehensive-comparison-of-deep-learning","title":"Comprehensive Comparison of Deep Learning Models for Lung and COVID-19 Lesion Segmentation in CT scans","date":"2020-09-10","arxiv_id":"2009.06412","n_code_links":1,"syntology":null},{"paper":"/paper/do-response-selection-models-really-know-what","slug":"do-response-selection-models-really-know-what","title":"Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection","date":"2020-09-10","arxiv_id":"2009.04703","n_code_links":1,"syntology":null},{"paper":"/paper/filter-an-enhanced-fusion-method-for-cross","slug":"filter-an-enhanced-fusion-method-for-cross","title":"FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding","date":"2020-09-10","arxiv_id":"2009.05166","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"investigating-gender-bias-in-bert","title":"Investigating Gender Bias in BERT","date":"2020-09-10","arxiv_id":"2009.05021","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-universal-representations-from-word","title":"Learning Universal Representations from Word to Sentence","date":"2020-09-10","arxiv_id":"2009.04656","n_code_links":0,"syntology":null},{"paper":"/paper/modern-methods-for-text-generation","slug":"modern-methods-for-text-generation","title":"Modern Methods for Text Generation","date":"2020-09-10","arxiv_id":"2009.04968","n_code_links":2,"syntology":null},{"paper":"/paper/rank-over-class-the-untapped-potential-of","slug":"rank-over-class-the-untapped-potential-of","title":"Rank over Class: The Untapped Potential of Ranking in Natural Language Processing","date":"2020-09-10","arxiv_id":"2009.05160","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["atapour/rank-over-class"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sparsifying-transformer-models-with","slug":"sparsifying-transformer-models-with","title":"Sparsifying Transformer Models with Trainable Representation Pooling","date":"2020-09-10","arxiv_id":"2009.05169","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-domain-adaptation-via-cyclegan","title":"Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images","date":"2020-09-10","arxiv_id":"2009.04985","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-study-of-language-models-on-cross","title":"Comparative Study of Language Models on Cross-Domain Data with Model Agnostic Explainability","date":"2020-09-09","arxiv_id":"2009.04095","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-each-layer-non-trivial-in-cnn","title":"Is Each Layer Non-trivial in CNN?","date":"2020-09-09","arxiv_id":"2009.09938","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-so-biggan-generating-high-fidelity-images","title":"not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution","date":"2020-09-09","arxiv_id":"2009.04433","n_code_links":0,"syntology":null},{"paper":"/paper/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","n_code_links":2,"syntology":null},{"paper":null,"slug":"ernie-at-semeval-2020-task-10-learning-word","title":"ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model","date":"2020-09-08","arxiv_id":"2009.03706","n_code_links":0,"syntology":null},{"paper":"/paper/masked-label-prediction-unified-massage","slug":"masked-label-prediction-unified-massage","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","date":"2020-09-08","arxiv_id":"2009.03509","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PaddlePaddle/PGL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/adversarial-watermarking-transformer-towards","slug":"adversarial-watermarking-transformer-towards","title":"Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding","date":"2020-09-07","arxiv_id":"2009.03015","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"black-box-to-white-box-discover-model","title":"Black Box to White Box: Discover Model Characteristics Based on Strategic Probing","date":"2020-09-07","arxiv_id":"2009.03136","n_code_links":0,"syntology":null},{"paper":"/paper/deep-cyclic-generative-adversarial-residual","slug":"deep-cyclic-generative-adversarial-residual","title":"Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution","date":"2020-09-07","arxiv_id":"2009.03693","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["RaoUmer/SRResCycGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deepfake-detection-humans-vs-machines","title":"Deepfake detection: humans vs. machines","date":"2020-09-07","arxiv_id":"2009.03155","n_code_links":0,"syntology":null},{"paper":null,"slug":"e-bert-a-phrase-and-product-knowledge","title":"E-BERT: A Phrase and Product Knowledge Enhanced Language Model for E-commerce","date":"2020-09-07","arxiv_id":"2009.02835","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-generation-with-sentence","slug":"improving-language-generation-with-sentence","title":"Improving Language Generation with Sentence Coherence Objective","date":"2020-09-07","arxiv_id":"2009.06358","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-massive-multitask-language","slug":"measuring-massive-multitask-language","title":"Measuring Massive Multitask Language Understanding","date":"2020-09-07","arxiv_id":"2009.03300","n_code_links":18,"syntology":{"ran":19,"of":26,"n_ran_checked":15,"n_instrument":4,"unverified":7,"pointer_only":1,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["hendrycks/test"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"5cfcb64884e775774075cef08061f5ced02eeb2397597c9b6ad1b6003d22457e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}